Anthropic's Transformer Circuits publishes new interpretability paper on the geometry of counting
burny_tech · x · 2026-10-27
Transformer Circuits Thread released a new interpretability paper, "When Models Manipulate Manifolds: The Geometry of a Counting Task," analyzing how models represent counting tasks geometrically. Commenter burnytech argues the field needs more exact algorithm-level explanations — like the trigonometric algorithm in the grokking modular addition toy model — rather than manifold descriptions alone.
Related event: Transformer Circuits Paper Examines Manifold Geometry of Counting(3 posts)→
More from Research
- Kevin Bryan: maximizing raw accuracy is rarely the right way to train AI assistants — Afinetheorem · 2026-10-27
- Szegedy: a flaw in common training losses went unnoticed for over a decade — ChrSzegedy · 2026-10-27
- Claude research model claims to refute Exponential Time Hypothesis with 14M-token autonomous run — scaling01 · 2026-10-27
- "ETH is false": CS community buzzing over claim that upends SAT exponential-time assumption — akbirthko · 2026-10-27
- RL environments essay: knowing how to operate software isn't knowing how to achieve goals — ShenRaphael · 2026-10-27
- Δτ-Bench: Agents Face a Moving Tool Frontier, Best Model Scores Just 42.3% — UniversityCollegeLondon · 2026-10-27